© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8164
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÐľÐŀ
    -0.25
    mö
    -0.24
    ksz
    -0.24
     Malk
    -0.23
     HttpRequest
    -0.23
     XmlDocument
    -0.23
    -relative
    -0.23
     Race
    -0.23
    Race
    -0.23
    -rule
    -0.23
    POSITIVE LOGITS
    æ³¥
    0.28
    ddl
    0.27
     citations
    0.27
    hammer
    0.26
    backs
    0.26
    aver
    0.25
    åľ¨åºĬä¸Ĭ
    0.25
    pbs
    0.24
    ɵ
    0.24
    iams
    0.24
    Activations Density 0.000%

    No Known Activations